Dmitry.AI

What does mean «faster_rcnn» → «image_resizer» → «keep_aspect_ratio_resizer» in TensorFlow?

computer-vision
object-detection
сonvolutional-neural-network
training
tensorflow-image-resizer
tensorflow
faster-rcnn
tensorflow-api
tensorflow-object-detection
(Dmitry Fedyuk) #1
What does mean «faster_rcnn» → «image_resizer» in TensorFlow?
(Dmitry Fedyuk) #2

What does mean «faster_rcnn» → «image_resizer» in TensorFlow?

Specifying the keep_aspect_ratio_resizer follows the image resizing scheme described in the Faster R-CNN paper.
In this case it always resizes an image so that the smaller edge is 600 pixels and if the longer edge is greater than 1024 edges, it resizes such that the longer edge is 1024 pixels.
The resulting image always has the same aspect ratio as the input image.

github.com/tensorflow/models/issues/1794#issuecomment-311569473

The bounding box coordinates are normalised to the range [0 … 1], so resizing the images won’t affect those annotations.
Masks are resized or otherwise transformed along with the image, and always have the same dimensions as the image.

github.com/tensorflow/models/issues/1794#issuecomment-432929170

(Dmitry Fedyuk) #3

See also: